Sotabase

Career

· Senior Research Scientist, MIT-IBM Watson AI Lab2024–
· Member, Harvard University Program in Speech and Hearing Bioscience and Technology
· Leader of Spoken Language Systems Group, MIT CSAIL
· Senior Research Scientist, MIT CSAIL
· Researcher, MIT CSAIL - Multicore Algorithmics Group
· Ph.D. and S.M. graduate, MIT (Electrical Engineering and Computer Science)

Publications (451)

AST: Audio Spectrogram Transformer
Interspeech · 2021
1,188
cited
Speech database development at MIT: Timit and beyond
Speech Communication · 1990
647
cited
Analysis Methods in Neural Language Processing: A Survey
Transactions of the Association for Computational Linguistics · 2018
599
cited
JUPlTER: a telephone-based conversational interface for weather information
IEEE Transactions on Speech and Audio Processing · 2000
558
cited
What do Neural Machine Translation Models Learn about Morphology?
Annual Meeting of the Association for Computational Linguistics · 2017
429
cited
An Unsupervised Autoregressive Model for Speech Representation Learning
Interspeech · 2019
425
cited
Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams
2009 IEEE Workshop on Automatic Speech Recognition & Understanding · 2009
374
cited
Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
Neural Information Processing Systems · 2017
369
cited
SSAST: Self-Supervised Audio Spectrogram Transformer
AAAI Conference on Artificial Intelligence · 2021
364
cited
Unsupervised Pattern Discovery in Speech
IEEE Transactions on Audio, Speech, and Language Processing · 2008
360
cited
A probabilistic framework for segment-based speech recognition
Computer Speech and Language · 2003
342
cited
Highway long short-term memory RNNS for distant speech recognition
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2015
296
cited
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
International Conference on Learning Representations · 2023
292
cited
Detecting Depression with Audio/Text Sequence Modeling of Interviews
Interspeech · 2018
281
cited
Robust Speaker Recognition in Noisy Conditions
IEEE Transactions on Audio, Speech, and Language Processing · 2007
279
cited
Predicting Factuality of Reporting and Bias of News Media Sources
Conference on Empirical Methods in Natural Language Processing · 2018
262
cited
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
North American Chapter of the Association for Computational Linguistics · 2022
257
cited
Unsupervised Learning of Spoken Language with Visual Context
Neural Information Processing Systems · 2016
256
cited
A Nonparametric Bayesian Approach to Acoustic Model Discovery
Annual Meeting of the Association for Computational Linguistics · 2012
231
cited
Cosine Similarity Scoring without Score Normalization Techniques
The Speaker and Language Recognition Workshop · 2010
224
cited
Sotabase